Publikation

Learning Dialogue Agents with Bayesian Relational State Representations

Dr. Heriberto Cuayáhuitl

In: Proceedings of the IJCAI Workshop on Knowledge and Reasoning in Practical Dialogue Systems (IJCAI-KRPDS). IJCAI Workshop on Knowledge and Reasoning in Practical Dialogue Systems (KRPD-2011) 7th July 16-22 Barcelona Spain Seiten 9-15 IJCAI 7/2011.

Abstrakt

A new approach is developed for representing the search space of reinforcement learning dialogue agents. This approach represents the state-action space of a reinforcement learning dialogue agent with relational representations for fast learning, and extends it with belief state variables for dialogue control under uncertainty. Our approach is evaluated, using simulation, on a spoken dialogue system for situated indoor wayfinding assistance. Experimental results showed rapid adaptation to an unknown speech recognizer, and more robust operation than without Bayesian-based states.

Projekte

hc-ijcai-krpds2011.pdf (pdf, 719 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence